vLLM Releases Kimi K3 Deployment Guide: Supports B300 and MI355X

vllm_project · x · 2026-07-30

The vLLM team released a detailed technical guide for Day-0 support of the Kimi K3 model. Kimi K3 is a 2.8-trillion-parameter Mixture-of-Experts model with 16 active experts per token, featuring a 1M-token context window and native vision.

The post dives into how vLLM adapts to Kimi K3's unique KDA and AttnRes architecture, tackling deployment challenges like MXFP4 MoE, KV cache management, and prefill/decode disaggregation. It recommends running on 8 NVIDIA B300 or AMD MI355X GPUs and supports open-source DSpark speculative decoding acceleration provided by Inferact.

Related event: Kimi K3 Open-Sourced with Day-0 Native Support from vLLM and AMD(11 posts)→

Original post →

More from Infra

Infra channel →